I didn't want to pay a monthly subscription for dictation, so I built one that runs on my GPU
说明与用途
Wisperno 是一款在 Windows PC 上使用 NVIDIA GPU 的离线语音转文字应用,避免订阅和网络请求。它使用 Whisper large‑v3‑turbo 和量化语言模型,100 字的延迟为 0.82‑1.48 秒,实时转录模式速度为 13.5 倍。
问题
Need offline, subscription‑free dictation on a PC
结果
Runs fully offline on NVIDIA GPU, 0.82‑1.48 s latency for 100 words, 97.6‑98.8 % fidelity, 13.5× faster than real time in live mode
工作流
- Hold hotkey
- Speak
- Release
- Text pasted into focused app
- Optional polish via local model
证据
It runs fully offline. Whisper large‑v3‑turbo transcribes on the GPU, and a small quantized language model cleans up the text.
A long pause (1.3 seconds or more) starts a new paragraph. I first tried segment‑level timestamps from Whisper to detect the pause, and they could not see it at all. Word‑level timestamps can.
The smaller presets are faster and use less memory. The bigger ones keep a little more fidelity: 97.6% for the two smallest, 98.8% for the two 3B models, measured on raw model output.
Live Transcription is a separate mode for meetings and lectures. My first design re‑decoded only a sliding window of the latest audio. The test suite showed it silently dropped real words. The current version re‑decodes the whole unconfirmed audio buffer every 0.6 seconds. It runs about 13.5 times faster than real time (RTF 0.074), with no second model loaded.
- 记录日期: 2026-10-21T14:41:05.380Z